INDEX

Explanations

sections clearly labeled as pros and cons in reviews or evaluations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Trot

-0.18

æĿ¿

-0.16

ÏģÎ¯Î¿Ïħ

-0.15

 cour

-0.15

ullo

-0.15

zell

-0.14

ÏģÎ¸

-0.14

heim

-0.14

ÑİÑĢ

-0.13

Ð»Ð»

-0.13

POSITIVE LOGITS

outh

0.16

olta

0.14

owler

0.14

rypton

0.14

outu

0.13

 ranked

0.13

edy

0.13

 champs

0.13

 stringWithFormat

0.13

 tritur

0.13

Activations Density 0.001%

sections clearly labeled as pros and cons in reviews or evaluations

No Comments

No Known Activations